Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1290 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.2511. Min Range: -5.2511

Max Act: 5.2511. Min Act: -0.1700

Data Index: 428775 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 5.2511. Min Range: -5.2511

Max Act: 5.2198. Min Act: -0.1700

Data Index: 983496 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 5.2511. Min Range: -5.2511

Max Act: 5.0948. Min Act: -0.1700

Data Index: 1229358 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 5.2511. Min Range: -5.2511

Max Act: 5.0636. Min Act: -0.1700

Data Index: 1107308 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 5.2511. Min Range: -5.2511

Max Act: 5.0011. Min Act: -0.1700

Data Index: 638708 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 5.2511. Min Range: -5.2511

Max Act: 5.0636. Min Act: -0.1700

Data Index: 37108 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 5.2511. Min Range: -5.2511

Max Act: 5.1261. Min Act: -0.1700

Data Index: 105008 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 5.2511. Min Range: -5.2511

Max Act: 5.0011. Min Act: -0.1700

Data Index: 119618 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 5.2511. Min Range: -5.2511

Max Act: 4.9386. Min Act: -0.1700

Data Index: 58036 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 5.2511. Min Range: -5.2511

Max Act: 4.9386. Min Act: -0.1700

Data Index: 562203 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 5.2511. Min Range: -5.2511

Max Act: 4.9698. Min Act: -0.1700

Data Index: 528886 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 5.2511. Min Range: -5.2511

Max Act: 4.9073. Min Act: -0.1700

Data Index: 158549 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 5.2511. Min Range: -5.2511

Max Act: 4.9386. Min Act: -0.1700

Data Index: 1122678 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 5.2511. Min Range: -5.2511

Max Act: 4.8448. Min Act: -0.1700

Data Index: 971372 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 5.2511. Min Range: -5.2511

Max Act: 4.8448. Min Act: -0.1700

Data Index: 84896 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 5.2511. Min Range: -5.2511

Max Act: 4.7823. Min Act: -0.1700

Data Index: 511807 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 5.2511. Min Range: -5.2511

Max Act: 4.7823. Min Act: -0.1700

Data Index: 947057 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 5.2511. Min Range: -5.2511

Max Act: 4.7823. Min Act: -0.1700

Data Index: 39314 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 5.2511. Min Range: -5.2511

Max Act: 4.8136. Min Act: -0.1700

Data Index: 799982 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 5.2511. Min Range: -5.2511

Max Act: 4.7511. Min Act: -0.1700

Data Index: 1095125 (C4 (Web Text))

Max Activating Token Index: 142